CN109859774A - Speech ciphering equipment and its end-point detection sensitivity adjustment method, device and storage medium - Google Patents
Speech ciphering equipment and its end-point detection sensitivity adjustment method, device and storage medium Download PDFInfo
- Publication number
- CN109859774A CN109859774A CN201910002054.4A CN201910002054A CN109859774A CN 109859774 A CN109859774 A CN 109859774A CN 201910002054 A CN201910002054 A CN 201910002054A CN 109859774 A CN109859774 A CN 109859774A
- Authority
- CN
- China
- Prior art keywords
- ciphering equipment
- speech
- speech ciphering
- user
- detection sensitivity
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Abstract
The present invention provides a kind of speech ciphering equipment and its end-point detection sensitivity adjustment method, device and storage medium, which comprises obtains wakeup time when user successfully wakes up the speech ciphering equipment every time；Wakeup time when successfully waking up the speech ciphering equipment every time according to the user analyzes user to the use habit of the speech ciphering equipment；The adjusting strategy of the speech terminals detection sensitivity of the speech ciphering equipment is set according to use habit of the user to the speech ciphering equipment；According to the speech terminals detection sensitivity of speech ciphering equipment described in the adjusting strategy adjustment.Scheme provided by the invention can avoid meaningless speech processes in the case where speech ciphering equipment is to wake-up states according to the sensitivity of the speech ciphering equipment use habit automatic adjusument speech terminals detection of user.
Description
Technical field
The present invention relates to control field more particularly to a kind of speech ciphering equipments and its end-point detection sensitivity adjustment method, dress
It sets and storage medium.
Background technique
There is a problem of that noise is big in remote speech identification process, due to needing to detect ambient sound at any time and identifying language
Justice, so using voice activity detection algorithm and setting wake-up word to reduce false recognition rate.Speech terminals detection (Voice
Activity Detection, VAD), i.e., by efficient voice (that is, people's one's voice in speech) from continuous voice flow
Part is either mute separated with extraneous noise, reduces the data volume of storage or transmission, negative with the calculating for reducing equipment
It carries, realizes the quick identification of voice.Wake-up word, which refers to, to be needed before voice control through preset wake-up word elder generation wake-up device,
To avoid accidentally control, such as " day cat is smart ", " small love classmate ", " Gree gold shellfish " etc..It is existing wait call out under routine use environment
Wake up state under speech terminals detection sensitivity be constant, can not automatic adjusument, this is unreasonable.Since user is in difference
Period is different the frequency of use of equipment, i.e., user is different in wakeup frequency of the different time sections to equipment, if
Identical end-point detection sensitivity, which is arranged, will form unnecessary power wastage.
Summary of the invention
It is a primary object of the present invention to overcome the defect of the above-mentioned prior art, a kind of speech ciphering equipment and its endpoint inspection are provided
Sensitivity adjustment method, device and storage medium are surveyed, to solve in the prior art to the speech terminals detection under wake-up states, no
Time segment is respectively provided with the problem of identical end-point detection sensitivity will form unnecessary power wastage.
One aspect of the present invention provides a kind of end-point detection sensitivity adjustment method of speech ciphering equipment, comprising: obtains user
The wakeup time when speech ciphering equipment is successfully waken up every time；When successfully waking up the speech ciphering equipment every time according to the user
Wakeup time analyzes user to the use habit of the speech ciphering equipment；According to the user to the use habit of the speech ciphering equipment
The adjusting strategy of the speech terminals detection sensitivity of the speech ciphering equipment is set；It is set according to voice described in the adjusting strategy adjustment
Standby speech terminals detection sensitivity.
Optionally, wakeup time when successfully waking up the speech ciphering equipment every time according to the user analyzes user to described
The use habit of speech ciphering equipment, comprising: successfully wake up the wakeup time when speech ciphering equipment every time according to user, analyze user
The wake-up probability of each period in multiple preset time periods to the speech ciphering equipment.
Optionally, the sound end of the speech ciphering equipment is set according to use habit of the user to the speech ciphering equipment
The adjusting strategy of detection sensitivity, comprising: according to each period of the user in multiple preset time periods to institute's predicate
The corresponding speech terminals detection sensitivity of the multiple preset time period is respectively set in the wake-up probability of sound equipment.
Optionally, the speech terminals detection sensitivity of the speech ciphering equipment according to the adjusting strategy adjustment, comprising: determine
Current time first time period locating in the multiple preset time period；When obtaining described first according to the adjusting strategy
Between the first speech terminals detection sensitivity corresponding to section；The voice is set by the first speech terminals detection sensitivity
The current speech terminals detection sensitivity of equipment.
Optionally, the multiple preset time period, comprising: daily and/or daily multiple periods weekly.
Another aspect of the present invention provides a kind of end-point detection switch-operated response control of speech ciphering equipment, comprising: obtains single
Member, for obtaining wakeup time when user successfully wakes up the speech ciphering equipment every time；Analytical unit, for according to the user
Wakeup time when successfully waking up the speech ciphering equipment every time analyzes user to the use habit of the speech ciphering equipment；Setting is single
Member, the speech terminals detection for the speech ciphering equipment to be arranged according to use habit of the user to the speech ciphering equipment are sensitive
The adjusting strategy of degree；Unit is adjusted, the speech terminals detection for the speech ciphering equipment according to the adjusting strategy adjustment is sensitive
Degree.
Optionally, the analytical unit successfully wakes up the wakeup time when speech ciphering equipment according to the user every time
User is analyzed to the use habit of the speech ciphering equipment, comprising: calling out when successfully waking up the speech ciphering equipment every time according to user
It wakes up the time, analyzes each period of the user in multiple preset time periods to the wake-up probability of the speech ciphering equipment.
Optionally, the voice is arranged according to use habit of the user to the speech ciphering equipment in the setting unit
The adjusting strategy of the speech terminals detection sensitivity of equipment, comprising: according to the user in each of multiple preset time periods
Period, each period being respectively set in the multiple preset time period was corresponding to the wake-up probability of the speech ciphering equipment
Speech terminals detection sensitivity.
Optionally, the adjusting unit, comprising: subelement is determined, for determining current time when the multiple default
Between first time period locating in section；Subelement is obtained, it is right for obtaining the first time period institute according to the adjusting strategy
The the first speech terminals detection sensitivity answered；Subelement is set, for setting the first speech terminals detection sensitivity to
The current speech terminals detection sensitivity of the speech ciphering equipment.
Optionally, the multiple preset time period, comprising: daily and/or daily multiple periods weekly.
Another aspect of the invention provides a kind of storage medium, is stored thereon with computer program, and described program is processed
The step of device realizes aforementioned any the method when executing.
Further aspect of the present invention provides a kind of speech ciphering equipment, including processor, memory and storage are on a memory
The computer program that can be run on a processor, the processor realize the step of aforementioned any the method when executing described program
Suddenly.
Further aspect of the present invention provides a kind of speech ciphering equipment, the end-point detection including aforementioned any speech ciphering equipment
Switch-operated response control.
According to the technique and scheme of the present invention, is arranged by speech ciphering equipment endpoint and is examined for the use habit of speech ciphering equipment based on user
Sensitivity automatic adjusument strategy is surveyed, it can be in the case where speech ciphering equipment waits for wake-up states, according to user's use habit automatic adjusument
The sensitivity of speech terminals detection；Also, the time that speech ciphering equipment is waken up by counting user, summarize user in different time sections
To the wakeup frequency of speech ciphering equipment, so that user is analyzed to the use habit of speech ciphering equipment, thus, voice is being not frequently used
When equipment, speech terminals detection sensitivity is reduced, when the equipment is commonly used, speech terminals detection sensitivity is improved, avoids
Meaningless speech processes.
Detailed description of the invention
The drawings described herein are used to provide a further understanding of the present invention, constitutes a part of the invention, this hair
Bright illustrative embodiments and their description are used to explain the present invention, and are not constituted improper limitations of the present invention.In the accompanying drawings:
Fig. 1 is the method signal of an embodiment of the end-point detection sensitivity adjustment method of speech ciphering equipment provided by the invention
Figure；
Fig. 2 be it is according to an embodiment of the present invention seven days a week in daily each preset period of time user wake up described set
The histogram of standby wake-up probability number；
Fig. 3 is the cake chart of the wake-up probability of daily multiple periods according to an embodiment of the present invention；
Fig. 4 be it is according to an embodiment of the present invention seven days a week in daily user wake up the wake-up probability of the speech ciphering equipment
Cake chart；
Fig. 5 is the speech terminals detection of the speech ciphering equipment according to an embodiment of the present invention according to the adjusting strategy adjustment
The flow diagram of the specific embodiment of the step of sensitivity；
Fig. 6 is the structural representation of an embodiment of the end-point detection switch-operated response control of speech ciphering equipment provided by the invention
Figure；
Fig. 7 is the structural schematic diagram of the specific embodiment according to an embodiment of the present invention for adjusting unit.
Specific embodiment
To make the object, technical solutions and advantages of the present invention clearer, below in conjunction with the specific embodiment of the invention and
Technical solution of the present invention is clearly and completely described in corresponding attached drawing.Obviously, described embodiment is only the present invention one
Section Example, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art are not doing
Every other embodiment obtained under the premise of creative work out, shall fall within the protection scope of the present invention.
It should be noted that description and claims of this specification and term " first " in above-mentioned attached drawing, "
Two " etc. be to be used to distinguish similar objects, without being used to describe a particular order or precedence order.It should be understood that using in this way
Data be interchangeable under appropriate circumstances, so as to the embodiment of the present invention described herein can in addition to illustrating herein or
Sequence other than those of description is implemented.In addition, term " includes " and " having " and their any deformation, it is intended that cover
Cover it is non-exclusive include, for example, the process, method, system, product or equipment for containing a series of steps or units are not necessarily limited to
Step or unit those of is clearly listed, but may include be not clearly listed or for these process, methods, product
Or other step or units that equipment is intrinsic.
Fig. 1 is the method signal of an embodiment of the end-point detection sensitivity adjustment method of speech ciphering equipment provided by the invention
Figure.
As shown in Figure 1, according to one embodiment of present invention, the end-point detection sensitivity adjustment method of the speech ciphering equipment
Including at least step S110, step S120, step S130 and step S140.
Step S110 obtains wakeup time when user wakes up the speech ciphering equipment every time.
The speech ciphering equipment can be the equipment of distribution, keep connected state.Described in successfully being waken up every time as user
When speech ciphering equipment, acquisition user successfully wakes up the wakeup time when speech ciphering equipment, and is recorded.Preferably, the is obtained
Wakeup time when user wakes up the speech ciphering equipment every time in one preset time, for example, obtaining in one month or a season
Interior user wakes up the wakeup time when speech ciphering equipment every time.
Step S120, wakeup time when waking up the speech ciphering equipment every time according to the user analyze user to institute's predicate
The use habit of sound equipment.
Specifically, it successfully wakes up the wakeup time when speech ciphering equipment every time according to user, analyzes user multiple pre-
If each period in the period is to the wake-up probability of the speech ciphering equipment.More specifically, being counted respectively the multiple pre-
If each preset time period user in the period successfully wakes up the wake-up times of the speech ciphering equipment, according to each preset time
Section user successfully wakes up the wake-up times of the speech ciphering equipment and user successfully wakes up the total degree of the speech ciphering equipment, determines
User is in each preset time period to the wake-up probability of the speech ciphering equipment.Wherein, the multiple preset time period specifically can be with
It include: daily and/or daily multiple periods weekly.
For example, counting each period user in multiple preset period of time in seven days a week daily respectively successfully wakes up institute's predicate
The wake-up times of sound equipment, for example, being divided into 8:00-12:00,12:00-18:00,18:00-23:00,23:00-8 for one day:
00 4 periods, each period user for counting daily in seven days a week respectively successfully wake up the wake-up time of the speech ciphering equipment
Number, thus successfully waken up according to user the speech ciphering equipment total wake-up times and seven days a week in daily each period use
Family successfully wakes up the wake-up times of the speech ciphering equipment, calculates the wake-up probability of each period daily in seven days a week.For example,
Fig. 2 be it is according to an embodiment of the present invention seven days a week in daily each preset period of time user wake up the wake-up of the default equipment
The histogram of number.
In another example multiple periods were divided by one day, such as 8:00-12:00,12:00-18:00,18:00-23:00,23:
Tetra- periods of 00-8:00, each period user for counting daily respectively successfully wake up the wake-up times of the speech ciphering equipment, thus
The total wake-up times and each period user that the speech ciphering equipment is successfully waken up according to user successfully wake up the speech ciphering equipment
Total wake-up times calculate the wake-up probability of each period.For example, Fig. 3 is daily multiple periods according to an embodiment of the present invention
Wake-up probability cake chart.Fig. 3, which can be the daily each period user counted according to fig. 2 and successfully wake up the voice, to be set
Standby wake-up times obtain.As shown in figure 3, user is likely to be at sleep state in morning (23:00-8:00), probability is waken up most
Low, user may be since it is not high to wake up probability during being working on daytime (8:00-12:00,12:00-18:00).User is in evening
Upper (18:00-23:00) is likely to be at the state of going home, and wakes up probability highest.
In another example the wake-up times that daily user in seven days a week successfully wakes up the speech ciphering equipment are counted respectively, thus
Successfully waken up according to user the speech ciphering equipment total wake-up times and seven days a week in daily user successfully wake up institute's predicate
The wake-up times of sound equipment calculate wake-up probability daily in seven days a week.For example, Fig. 4 is according to an embodiment of the present invention every
Daily user wakes up the cake chart of the wake-up probability of the speech ciphering equipment in Zhou Qitian.Fig. 4 can be to be counted weekly according to fig. 2
The wake-up times that daily user successfully wakes up the speech ciphering equipment in seven days obtain.As shown in figure 4, user is in Saturday, Sunday one
As in having a holiday or vacation state, wake up probability highest, user is likely to be at work state the most busy in Wednesday, wakes up probability most
It is low.
The end-speech of the speech ciphering equipment is arranged according to use habit of the user to the speech ciphering equipment by step S130
The adjusting strategy of point detection sensitivity.
Specifically, the strategy that adjusts includes the corresponding sound end of each period in the multiple preset time period
Detection sensitivity.It is general to the wake-up of the speech ciphering equipment according to each period of the user in multiple preset time periods
Rate, corresponding speech terminals detection sensitivity of each period being respectively set in the multiple preset time period.That is,
Different speech terminals detection sensitivity is arranged in the preset time period that difference wakes up probability.Wherein, the probability higher time is waken up
The period of the speech ciphering equipment is commonly used in section, i.e. user, and higher speech terminals detection sensitivity is arranged, and it is lower to wake up probability
Period, i.e. user's period that the speech ciphering equipment is not frequently used, lower speech terminals detection sensitivity is set.
Step S140, according to the speech terminals detection sensitivity of speech ciphering equipment described in the adjusting strategy adjustment.
Fig. 5 is the speech terminals detection of the speech ciphering equipment according to an embodiment of the present invention according to the adjusting strategy adjustment
The flow diagram of the specific embodiment of the step of sensitivity.As shown in figure 5, step S140 specifically include step S141,
Step S142 and step S143.
Step S141 determines current time first time period locating in the multiple preset time period.
Step S142 obtains the spirit of the first speech terminals detection corresponding to the first time period according to the adjusting strategy
Sensitivity.
The first speech terminals detection sensitivity is set the current sound end of the speech ciphering equipment by step S143
Detection sensitivity.
For example, if in such a way that above-mentioned one day is divided into multiple periods, when determining that current time is locating in one day
Between section, for example, current time be 9:00, be in the 8:00-12:00 period, then obtain 8:00-12:00 period corresponding end-speech
Point detection sensitivity, and it is set as current speech terminals detection sensitivity.In another example if according to above-mentioned division seven days a week
Mode determines the current time period locating in seven days a week, i.e., what day is currently, such as be currently Wednesday, then
Wednesday corresponding speech terminals detection sensitivity is obtained, and is set as current speech terminals detection sensitivity.In another example if
According to it is above-mentioned seven days a week in daily preset period of time division mode, first determine that current time is in week in seven days a week
It is several, then determine current time locating period in one day, for example, being currently Wednesday 9:00, then obtain in the adjusting strategy
The corresponding end-point detection sensitivity of the 8:00-12:00 period on Wednesday, and it is set as current speech terminals detection sensitivity.
Sound end inspection is carried out according to current speech terminals detection sensitivity after speech ciphering equipment receives and wakes up voice
It surveys.In a specific embodiment, language is carried out using the end-point detection technology based on short-time energy and the double threshold of zero-crossing rate
Voice endpoint detection.
Optionally, user in the first preset time is obtained again every the second preset time successfully wake up the voice every time
Wakeup time when equipment, and when successfully waking up the speech ciphering equipment every time according to user in the first preset time obtained again
Wakeup time update user to the use habit of the speech ciphering equipment, to update the speech terminals detection spirit of the speech ciphering equipment
The adjusting strategy of sensitivity.That is, updating the tune of the speech terminals detection sensitivity of the speech ciphering equipment at regular intervals
Section strategy.
For example, obtaining user again one month in every month or each season or successfully waking up the voice in a season
Wakeup time when equipment, and user successfully wakes up the voice every time and sets according to one month obtained again or in a season
Wakeup time when standby updates user to the use habit of the speech ciphering equipment, to reset the end-speech of the speech ciphering equipment
The adjusting strategy of point detection sensitivity.
Fig. 6 is the structural representation of an embodiment of the end-point detection switch-operated response control of speech ciphering equipment provided by the invention
Figure.As shown in fig. 6, the end-point detection switch-operated response control 100 of the speech ciphering equipment includes acquiring unit 110, analytical unit
120, setting unit 130 and adjusting unit 140.
Acquiring unit 110 is used to obtain wakeup time when user successfully wakes up the speech ciphering equipment every time；Analytical unit
120 analyze user to the speech ciphering equipment for wakeup time when successfully waking up the speech ciphering equipment every time according to the user
Use habit；Setting unit 130 is used to that the voice to be arranged according to use habit of the user to the speech ciphering equipment and sets
The adjusting strategy of standby speech terminals detection sensitivity；It adjusts unit 140 and is used for the voice according to the adjusting strategy adjustment
The speech terminals detection sensitivity of equipment.
Acquiring unit 110 obtains wakeup time when user successfully wakes up the speech ciphering equipment every time.The speech ciphering equipment
It can be the equipment of distribution, keep connected state.When user successfully wakes up the speech ciphering equipment every time, acquisition user at
Function wakes up the wakeup time when speech ciphering equipment, and is recorded.More specifically, acquiring unit 110 is available default
Wakeup time when user wakes up the speech ciphering equipment every time in time, for example, obtaining in one month or user in a season
The wakeup time when speech ciphering equipment is waken up every time.
Analytical unit 120 successfully wakes up the wakeup time analysis user couple when the speech ciphering equipment according to the user every time
The use habit of the speech ciphering equipment.Specifically, analytical unit 120 can successfully wake up the speech ciphering equipment according to user every time
When wakeup time, it is general to the wake-up of the speech ciphering equipment to analyze each preset time period of the user in multiple preset time periods
Rate.More specifically, each preset time period user counted in the multiple preset time period respectively successfully wakes up institute's predicate
The wake-up times of sound equipment successfully wake up wake-up times and the user of the speech ciphering equipment according to each preset time period user
Success wakes up the total degree of the speech ciphering equipment, determines that user is general in wake-up of each preset time period to the speech ciphering equipment
Rate.Wherein, the multiple preset time period can specifically include: daily and/or daily multiple periods weekly.
For example, counting each period user in multiple preset period of time in seven days a week daily respectively successfully wakes up institute's predicate
The wake-up times of sound equipment, for example, being divided into 8:00-12:00,12:00-18:00,18:00-23:00,23:00-8 for one day:
00 4 periods, each period user for counting daily in seven days a week respectively successfully wake up the wake-up time of the speech ciphering equipment
Number, thus successfully waken up according to user the speech ciphering equipment total wake-up times and seven days a week in daily each period use
Family successfully wakes up the wake-up times of the speech ciphering equipment, calculates the wake-up probability of each period daily in seven days a week.For example,
Fig. 2 be it is according to an embodiment of the present invention seven days a week in daily each preset period of time user wake up the wake-up of the default equipment
The histogram of number.
In another example multiple periods were divided by one day, such as 8:00-12:00,12:00-18:00,18:00-23:00,23:
Tetra- periods of 00-8:00, each period user for counting daily respectively successfully wake up the wake-up times of the speech ciphering equipment, thus
The total wake-up times and each period user that the speech ciphering equipment is successfully waken up according to user successfully wake up the speech ciphering equipment
Total wake-up times calculate the wake-up probability of each period.For example, Fig. 3 is daily multiple periods according to an embodiment of the present invention
Wake-up probability cake chart.Fig. 3, which can be the daily each period user counted according to fig. 2 and successfully wake up the voice, to be set
Standby wake-up times obtain.As shown in figure 3, user is likely to be at sleep state in morning (23:00-8:00), probability is waken up most
Low, user may be since it is not high to wake up probability during being working on daytime (8:00-12:00,12:00-18:00).User is in evening
Upper (18:00-23:00) is likely to be at the state of going home, and wakes up probability highest.
In another example the wake-up times that daily user in seven days a week successfully wakes up the speech ciphering equipment are counted respectively, thus
Successfully waken up according to user the speech ciphering equipment total wake-up times and seven days a week in daily user successfully wake up institute's predicate
The wake-up times of sound equipment calculate wake-up probability daily in seven days a week.For example, Fig. 4 is according to an embodiment of the present invention every
Daily user wakes up the cake chart of the wake-up probability of the speech ciphering equipment in Zhou Qitian.Fig. 4 can be to be counted weekly according to fig. 2
The wake-up times that daily user successfully wakes up the speech ciphering equipment in seven days obtain.As shown in figure 4, user is in Saturday, Sunday one
As in having a holiday or vacation state, wake up probability highest, user is likely to be at work state the most busy in Wednesday, wakes up probability most
It is low.
The voice of the speech ciphering equipment is arranged according to use habit of the user to the speech ciphering equipment for setting unit 130
The adjusting strategy of end-point detection sensitivity.Specifically, it is described adjust strategy include the multiple preset time period in it is each when
Between the corresponding speech terminals detection sensitivity of section.Setting unit 130 is according to the user in each of multiple preset time periods
Period, each period being respectively set in the multiple preset time period was corresponding to the wake-up probability of the speech ciphering equipment
Speech terminals detection sensitivity.That is, different speech terminals detection spirits is arranged in the different preset time periods for waking up probability
Sensitivity.Wherein, the probability higher period is waken up, i.e. higher language is arranged commonly using the period of the speech ciphering equipment in user
Voice endpoint detection sensitivity, the period that the speech ciphering equipment is not frequently used in wake-up probability lower period, i.e. user, setting
Lower speech terminals detection sensitivity.
Adjust the speech terminals detection sensitivity of the speech ciphering equipment according to the adjusting strategy adjustment of unit 140.Fig. 7 is
The structural schematic diagram of the specific embodiment according to an embodiment of the present invention for adjusting unit.As shown in fig. 7, adjusting unit 140
Including determining subelement 141, obtaining subelement 142 and setting subelement 143.
Determine subelement 141 for determining current time first time period locating in the multiple preset time period；
Subelement 142 is obtained to be used to obtain the spirit of the first speech terminals detection corresponding to the first time period according to the adjusting strategy
Sensitivity；Subelement 143 is set for setting the current language of the speech ciphering equipment for the first speech terminals detection sensitivity
Voice endpoint detection sensitivity.
For example, if determining that subelement 141 determines current time one in such a way that above-mentioned one day is divided into multiple periods
The locating period in it is in the 8:00-12:00 period for example, current time is 9:00, then obtains subelement 142 and obtain 8:
The corresponding speech terminals detection sensitivity of 00-12:00 period, setting subelement 143 are set to current sound end inspection
Survey sensitivity.In another example if determining that subelement 141 determines current time weekly according to above-mentioned division mode seven days a week
What day the locating period, i.e., is currently, such as be currently Wednesday in seven days, then obtains subelement 142 and obtain Wednesday
Corresponding speech terminals detection sensitivity, setting subelement 143 are set to current speech terminals detection sensitivity.Example again
Such as, if according to it is above-mentioned seven days a week in daily preset period of time division mode, first determine current time place in seven days a week
It in what day, then determines current time locating period in one day, for example, being currently Wednesday 9:00, then obtains the adjusting
The 8:00-12:00 period on Wednesday corresponding end-point detection sensitivity in strategy, and it is set as current speech terminals detection spirit
Sensitivity.
Sound end inspection is carried out according to current speech terminals detection sensitivity after speech ciphering equipment receives and wakes up voice
It surveys.In a specific embodiment, language is carried out using the end-point detection technology based on short-time energy and the double threshold of zero-crossing rate
Voice endpoint detection.Specific embodiment can refer to the aforementioned description to Fig. 6.
Optionally, it is each every the second preset time to obtain user in the first preset time again for the acquiring unit 110
Success wakes up the wakeup time when speech ciphering equipment, and the analytical unit 120 obtains again according to the acquiring unit 110
Wakeup time when user successfully wakes up the speech ciphering equipment every time in first preset time updates user to the speech ciphering equipment
Use habit, so that the setting unit 130 makes the speech ciphering equipment according to the user that the updating unit 120 updates
With habit, the adjusting strategy of the speech terminals detection sensitivity of the speech ciphering equipment is updated.That is, at regular intervals more
The adjusting strategy of the speech terminals detection sensitivity of the new speech ciphering equipment.
For example, obtaining user again one month in every month or each season or successfully waking up the voice in a season
Wakeup time when equipment, and user successfully wakes up the voice every time and sets according to one month obtained again or in a season
Wakeup time when standby updates user to the use habit of the speech ciphering equipment, to reset the end-speech of the speech ciphering equipment
The adjusting strategy of point detection sensitivity.
The present invention also provides correspond to the speech ciphering equipment end-point detection sensitivity adjustment method a kind of storage medium,
The step of being stored thereon with computer program, aforementioned any the method realized when described program is executed by processor.
The present invention also provides correspond to the speech ciphering equipment end-point detection sensitivity adjustment method a kind of speech ciphering equipment,
Including the computer program that processor, memory and storage can be run on a processor on a memory, the processor is held
The step of realizing aforementioned any the method when row described program.
The present invention also provides correspond to the speech ciphering equipment end-point detection switch-operated response control a kind of speech ciphering equipment,
End-point detection switch-operated response control including aforementioned any speech ciphering equipment.
Accordingly, scheme provided by the invention is waken up period and the number of speech ciphering equipment by counting user, analyzes user
Use habit.Based on user's use habit, speech ciphering equipment end-point detection sensitivity automatic adjusument strategy is set, it can be in voice
Equipment waits under wake-up states, according to the sensitivity of user's use habit automatic adjusument speech terminals detection, thus, infrequently
When using the equipment, sensitivity is reduced, when the equipment is commonly used, sensitivity is improved, avoids meaningless speech processes.
Function described herein can be implemented in hardware, the software executed by processor, firmware or any combination thereof.
If implemented in the software executed by processor, computer can be stored in using function as one or more instructions or codes
It is transmitted on readable media or via computer-readable media.Other examples and embodiment are wanted in the present invention and appended right
It asks in the scope and spirit of book.For example, due to the property of software, function described above can be used by processor,
Hardware, firmware, hardwired or the software implementation for appointing the combination of whichever to execute in these.In addition, each functional unit can integrate
In one processing unit, it is also possible to each unit to physically exist alone, can also be integrated in two or more units
In one unit.
In several embodiments provided herein, it should be understood that disclosed technology contents can pass through others
Mode is realized.Wherein, the apparatus embodiments described above are merely exemplary, such as the division of the unit, Ke Yiwei
A kind of logical function partition, there may be another division manner in actual implementation, for example, multiple units or components can combine or
Person is desirably integrated into another system, or some features can be ignored or not executed.Another point, shown or discussed is mutual
Between coupling, direct-coupling or communication connection can be through some interfaces, the INDIRECT COUPLING or communication link of unit or module
It connects, can be electrical or other forms.
The unit as illustrated by the separation member may or may not be physically separated, and fill as control
The component set may or may not be physical unit, it can and it is in one place, or may be distributed over multiple
On unit.It can some or all of the units may be selected to achieve the purpose of the solution of this embodiment according to the actual needs.
If the integrated unit is realized in the form of SFU software functional unit and sells or use as independent product
When, it can store in a computer readable storage medium.Based on this understanding, technical solution of the present invention is substantially
The all or part of the part that contributes to existing technology or the technical solution can be in the form of software products in other words
It embodies, which is stored in a storage medium, including some instructions are used so that a computer
Equipment (can for personal computer, server or network equipment etc.) execute each embodiment the method for the present invention whole or
Part steps.And storage medium above-mentioned includes: that USB flash disk, read-only memory (ROM, Read-Only Memory), arbitrary access are deposited
Reservoir (RAM, Random Access Memory), mobile hard disk, magnetic or disk etc. be various to can store program code
Medium.
The above description is only an embodiment of the present invention, is not intended to restrict the invention, for those skilled in the art
For member, the invention may be variously modified and varied.All within the spirits and principles of the present invention, it is made it is any modification,
Equivalent replacement, improvement etc., should be included within scope of the presently claimed invention.
Claims (13)
1. a kind of end-point detection sensitivity adjustment method of speech ciphering equipment characterized by comprising
Obtain wakeup time when user successfully wakes up the speech ciphering equipment every time；
Wakeup time when successfully waking up the speech ciphering equipment every time according to the user analyzes user to the speech ciphering equipment
Use habit；
The speech terminals detection sensitivity of the speech ciphering equipment is set according to use habit of the user to the speech ciphering equipment
Adjusting strategy；
According to the speech terminals detection sensitivity of speech ciphering equipment described in the adjusting strategy adjustment.
2. the method according to claim 1, wherein successfully waking up the speech ciphering equipment every time according to the user
When wakeup time analysis user to the use habit of the speech ciphering equipment, comprising:
It successfully wakes up the wakeup time when speech ciphering equipment every time according to user, analyzes user in multiple preset time periods
Wake-up probability of each period to the speech ciphering equipment.
3. according to the method described in claim 2, it is characterized in that, according to the user to the use habit of the speech ciphering equipment
The adjusting strategy of the speech terminals detection sensitivity of the speech ciphering equipment is set, comprising:
According to each period of the user in multiple preset time periods to the wake-up probability of the speech ciphering equipment, set respectively
Set the corresponding speech terminals detection sensitivity of each period in the multiple preset time period.
4. according to the method described in claim 3, it is characterized in that, the language of the speech ciphering equipment according to the adjusting strategy adjustment
Voice endpoint detection sensitivity, comprising:
Determine current time first time period locating in the multiple preset time period；
The first speech terminals detection sensitivity corresponding to the first time period is obtained according to the adjusting strategy；
The current speech terminals detection sensitivity of the speech ciphering equipment is set by the first speech terminals detection sensitivity.
5. according to the described in any item methods of claim 2-4, which is characterized in that the multiple preset time period, comprising: weekly
Daily and/or daily multiple periods.
6. a kind of end-point detection switch-operated response control of speech ciphering equipment characterized by comprising
Acquiring unit, for obtaining wakeup time when user successfully wakes up the speech ciphering equipment every time；
Analytical unit, for wakeup time analysis user when successfully waking up the speech ciphering equipment every time according to the user to institute
State the use habit of speech ciphering equipment；
Setting unit, for the end-speech of the speech ciphering equipment to be arranged according to use habit of the user to the speech ciphering equipment
The adjusting strategy of point detection sensitivity；
Unit is adjusted, the speech terminals detection sensitivity for the speech ciphering equipment according to the adjusting strategy adjustment.
7. device according to claim 6, which is characterized in that the analytical unit is successfully called out every time according to the user
Wake up the speech ciphering equipment when wakeup time analysis user to the use habit of the speech ciphering equipment, comprising:
It successfully wakes up the wakeup time when speech ciphering equipment every time according to user, analyzes user in multiple preset time periods
Wake-up probability of each period to the speech ciphering equipment.
8. device according to claim 7, which is characterized in that the setting unit, according to the user to the voice
The adjusting strategy of the speech terminals detection sensitivity of the speech ciphering equipment is arranged in the use habit of equipment, comprising:
According to each period of the user in multiple preset time periods to the wake-up probability of the speech ciphering equipment, set respectively
Set the corresponding speech terminals detection sensitivity of each period in the multiple preset time period.
9. device according to claim 8, which is characterized in that the adjusting unit, comprising:
Subelement is determined, for determining current time first time period locating in the multiple preset time period；
Subelement is obtained, for obtaining the first speech terminals detection corresponding to the first time period according to the adjusting strategy
Sensitivity；
Subelement is set, for setting the current end-speech of the speech ciphering equipment for the first speech terminals detection sensitivity
Point detection sensitivity.
10. according to the described in any item devices of claim 7-9, which is characterized in that the multiple preset time period, comprising: every
Daily and/or daily multiple periods in week.
11. a kind of storage medium, which is characterized in that it is stored thereon with computer program, it is real when described program is executed by processor
The step of existing claim 1-5 any the method.
12. a kind of speech ciphering equipment, which is characterized in that on a memory can be in processor including processor, memory and storage
The step of computer program of upper operation, the processor realizes claim 1-5 any the method when executing described program.
13. a kind of speech ciphering equipment, which is characterized in that the end-point detection including the speech ciphering equipment as described in claim 6-10 is any
Switch-operated response control.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910002054.4A CN109859774B (en) | 2019-01-02 | 2019-01-02 | Voice equipment and method and device for adjusting endpoint detection sensitivity thereof and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910002054.4A CN109859774B (en) | 2019-01-02 | 2019-01-02 | Voice equipment and method and device for adjusting endpoint detection sensitivity thereof and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109859774A true CN109859774A (en) | 2019-06-07 |
| CN109859774B CN109859774B (en) | 2021-04-02 |
Family
ID=66893736
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910002054.4A Active CN109859774B (en) | 2019-01-02 | 2019-01-02 | Voice equipment and method and device for adjusting endpoint detection sensitivity thereof and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109859774B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110459220A (en) * | 2019-08-26 | 2019-11-15 | 杭州涂鸦信息技术有限公司 | A kind of voice awakening method and system and readable storage medium storing program for executing, computer |
| CN111176743A (en) * | 2019-12-31 | 2020-05-19 | 云知声智能科技股份有限公司 | Wake-up performance optimization method and device based on user use habits |
| CN112185393A (en) * | 2020-09-30 | 2021-01-05 | 深圳供电局有限公司 | Voice recognition processing method for power supply intelligent client |
| CN112185365A (en) * | 2020-09-30 | 2021-01-05 | 深圳供电局有限公司 | Power supply intelligent client processing method and system |
| CN112185392A (en) * | 2020-09-30 | 2021-01-05 | 深圳供电局有限公司 | Voice recognition processing system for power supply intelligent client |
| CN112634897A (en) * | 2020-12-31 | 2021-04-09 | 青岛海尔科技有限公司 | Equipment awakening method and device, storage medium and electronic device |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103561175A (en) * | 2013-11-05 | 2014-02-05 | 广东欧珀移动通信有限公司 | Method using mobile terminal to carry out voice awakening and device thereof |
| CN105182809A (en) * | 2015-07-22 | 2015-12-23 | 小米科技有限责任公司 | Method for adjusting light transmittance of intelligent curtain, intelligent curtain and device |
| CN105516510A (en) * | 2015-12-31 | 2016-04-20 | 广东小天才科技有限公司 | Mobile terminal awakening method and device |
| CN108010515A (en) * | 2017-11-21 | 2018-05-08 | 清华大学 | A kind of speech terminals detection and awakening method and device |
| CN108847219A (en) * | 2018-05-25 | 2018-11-20 | 四川斐讯全智信息技术有限公司 | A kind of wake-up word presets confidence threshold value adjusting method and system |
| CN108962250A (en) * | 2018-09-26 | 2018-12-07 | 出门问问信息科技有限公司 | Audio recognition method, device and electronic equipment |
| CN108986805A (en) * | 2018-06-29 | 2018-12-11 | 百度在线网络技术（北京）有限公司 | Method and apparatus for sending information |
| CN109102806A (en) * | 2018-09-29 | 2018-12-28 | 百度在线网络技术（北京）有限公司 | Method, apparatus, equipment and computer readable storage medium for interactive voice |
-
2019
- 2019-01-02 CN CN201910002054.4A patent/CN109859774B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103561175A (en) * | 2013-11-05 | 2014-02-05 | 广东欧珀移动通信有限公司 | Method using mobile terminal to carry out voice awakening and device thereof |
| CN105182809A (en) * | 2015-07-22 | 2015-12-23 | 小米科技有限责任公司 | Method for adjusting light transmittance of intelligent curtain, intelligent curtain and device |
| CN105516510A (en) * | 2015-12-31 | 2016-04-20 | 广东小天才科技有限公司 | Mobile terminal awakening method and device |
| CN108010515A (en) * | 2017-11-21 | 2018-05-08 | 清华大学 | A kind of speech terminals detection and awakening method and device |
| CN108847219A (en) * | 2018-05-25 | 2018-11-20 | 四川斐讯全智信息技术有限公司 | A kind of wake-up word presets confidence threshold value adjusting method and system |
| CN108986805A (en) * | 2018-06-29 | 2018-12-11 | 百度在线网络技术（北京）有限公司 | Method and apparatus for sending information |
| CN108962250A (en) * | 2018-09-26 | 2018-12-07 | 出门问问信息科技有限公司 | Audio recognition method, device and electronic equipment |
| CN109102806A (en) * | 2018-09-29 | 2018-12-28 | 百度在线网络技术（北京）有限公司 | Method, apparatus, equipment and computer readable storage medium for interactive voice |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110459220A (en) * | 2019-08-26 | 2019-11-15 | 杭州涂鸦信息技术有限公司 | A kind of voice awakening method and system and readable storage medium storing program for executing, computer |
| CN111176743A (en) * | 2019-12-31 | 2020-05-19 | 云知声智能科技股份有限公司 | Wake-up performance optimization method and device based on user use habits |
| CN111176743B (en) * | 2019-12-31 | 2023-05-05 | 云知声智能科技股份有限公司 | Awakening performance optimization method and device based on user use habit |
| CN112185393A (en) * | 2020-09-30 | 2021-01-05 | 深圳供电局有限公司 | Voice recognition processing method for power supply intelligent client |
| CN112185365A (en) * | 2020-09-30 | 2021-01-05 | 深圳供电局有限公司 | Power supply intelligent client processing method and system |
| CN112185392A (en) * | 2020-09-30 | 2021-01-05 | 深圳供电局有限公司 | Voice recognition processing system for power supply intelligent client |
| CN112634897A (en) * | 2020-12-31 | 2021-04-09 | 青岛海尔科技有限公司 | Equipment awakening method and device, storage medium and electronic device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109859774B (en) | 2021-04-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109859774A (en) | Speech ciphering equipment and its end-point detection sensitivity adjustment method, device and storage medium | |
| CN106782554A (en) | Voice awakening method and device based on artificial intelligence | |
| CN107146611B (en) | Voice response method and device and intelligent equipment | |
| CN107567083B (en) | Method and device for performing power-saving optimization processing | |
| CN106445664A (en) | Application program management method and device | |
| CN109686368B (en) | Voice wake-up response processing method and device, electronic equipment and storage medium | |
| EP3885937A1 (en) | Response generation device, response generation method, and response generation program | |
| CN108074571A (en) | Sound control method, system and the storage medium of augmented reality equipment | |
| CN112489648A (en) | Wake-up processing threshold adjustment method, voice home appliance, and storage medium | |
| CN111968644A (en) | Intelligent device awakening method and device and electronic device | |
| CN105844106A (en) | Health prompting method and device | |
| CN110741387A (en) | Face recognition method and device, storage medium and electronic equipment | |
| KR20190007513A (en) | System for Recommendation of APP, User Terminal and Method Therefor | |
| CN111524513A (en) | Wearable device and voice transmission control method, device and medium thereof | |
| CN111681675A (en) | Dynamic data transmission method, device, equipment and storage medium | |
| CN110475033B (en) | Intelligent dialing method, device, equipment and computer readable storage medium | |
| CN111949323A (en) | Intelligent device awakening optimization method and device, intelligent device and storage medium | |
| CN111613217A (en) | Equipment recommendation method and device, electronic equipment and readable storage medium | |
| CN112488742A (en) | User attribute information prediction method and device, electronic equipment and storage medium | |
| CN111163219A (en) | Alarm clock processing method and device, storage medium and terminal | |
| CN110832918A (en) | User position identification method and device, storage medium and electronic equipment | |
| CN114073493A (en) | Physiological data acquisition method and device and wearable equipment | |
| CN114898755B (en) | Voice processing method and related device, electronic equipment and storage medium | |
| CN111739515A (en) | Voice recognition method, device, electronic device, server and related system | |
| CN107154996B (en) | Incoming call interception method and device, storage medium and terminal |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |